YLYongseok Lee

Yongseok Lee

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Yongseok Lee has a total of 10 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Enhancing propensity score analysis with data missing not at random: Introducing dual-forest proximity imputation

    by Yongseok Lee, Walter L. Leite

    Researchers using propensity score analysis (PSA) to estimate treatment effects using secondary data may have to handle data that are missing not at random (MNAR). Existing methods for PSA with MNAR data use logistic regression to model the missing data mechanisms, thus requiring manual specification of functional forms, and are difficult to implement with a large number of covariates. To overcome these limitations, this study proposes alternatives to existing methods by replacing logistic regression with a random forest. Also, it introduces the dual-forest proximity imputation method, which leverages two types of proximity matrices of random forest techniques and incorporates missingness pattern information in each matrix. Results from a Monte Carlo simulation show dual-forest proximity imputation’s enhanced bias reduction with various types of MNAR mechanisms as compared to existing and alternative methods. A case study is also provided using data from the National Longitudinal Survey of Youth (NLSY79).

  • Open Access

    A Simulation-Based Power Analysis for the Discordant-Sibling Random Intercept Cross-Lagged Panel Model in Family-Based Longitudinal Research

    by Yongseok Lee, Amy Loviska, Robert Duncan, Kristine Marceau

    Family-based longitudinal studies are increasingly used to investigate psychological and behavioral processes, and it is imperative to understand the power to detect effects in increasingly complex statistical models. The Discordant-Sibling Random Intercept Cross-Lagged Panel Model (DS RI-CLPM) extends the Random Intercept Cross-Lagged Panel Model to estimate longitudinal bidirectional associations by separating within- and between family-level components to control stable traits and sibling-shared family-level confounding. To inform study design in family-based research, we conducted a simulation-based power analysis varying the number of families and waves, sibling discordance, random intercept variance proportion, effect sizes, and variable’s non-normality. Power increased with both increase in families and waves, although effect size was the strongest determinant. Within-family cross-lagged effects were easier to detect than between-family effects, and joint detection required most conservative designs. Practical recommendations for numbers of families and waves are provided for longitudinal research on psychological and behavioral phenomena using the DS RI-CLPM.

  • Open Access

    Enhancing Propensity Score Analysis with data Missing Not at Random: Introducing Dual-Forest Proximity Imputation

    by Yongseok Lee, Walter Leite

    Researchers using propensity score analysis (PSA) to estimate treatment effects using secondary data may have to handle data that is missing not at random (MNAR). Existing methods for PSA with MNAR data use logistic regression to model the missing data mechanisms, thus requiring manual specification of functional forms, and are difficult to implement with a large number of covariates. To overcome these limitations, this study proposes alternatives to existing methods by replacing logistic regression with a random forest. Also, it introduces the Dual-Forest Proximity imputation method, which leverages two types of proximity matrices of random forest techniques and incorporates missing pattern information in each matrix. Results from a Monte Carlo simulation show Dual-Forest Proximity imputation’s enhanced bias reduction with various types of MNAR mechanisms as compared to existing and alternative methods. A case study is also provided using data from the National Longitudinal Survey of Youth 1979 (NLSY79).

  • Open Access

    Machine Learning for Propensity Score Estimation: A Systematic Review and Reporting Guidelines

    by Walter Leite, Huibin Zhang, Zachary Collier, Kamal Chawla, Yongseok Lee, Jia Quan, Olushola Soyoye

    Machine learning has become a common approach for estimating propensity scores for quasi-experimental research using matching, weighting, or stratification on the propensity score. This systematic review examined machine learning applications for propensity score estimation across different fields, such as health, education, social sciences, and business over 40 years. The results show that the gradient boosting machine (GBM) is the most frequently used method, followed by random forest. Classification and regression trees (CART), neural networks, and the super learner were also used in more than five percent of studies. The most frequently used packages to estimate propensity scores were twang, gbm and randomforest in the R statistical software. The review identified many hyperparameter configurations used for machine learning methods. However, it also shows that hyperparameters are frequently under-reported, as well as critical steps of the propensity score analysis, such as the covariate balance evaluation. A set of guidelines for reporting the use of machine learning for propensity score estimation is provided.


  • A comparison of random forest-based missing imputation methods for covariates in propensity score analysis.

    by Yongseok Lee, Walter L. Leite

    Propensity score analysis (PSA) is a prominent method to alleviate selection bias in observational studies, but missing data in covariates is prevalent and must be dealt with during propensity score estimation. Through Monte Carlo simulations, this study evaluates the use of imputation methods based on multiple random forests algorithms to handle missing data in covariates: multivariate imputation by chained equations-random forest (Caliber), proximity imputation (PI), and missForest. The results indicated that PI and missForest outperformed other methods with respect to bias of average treatment effect regardless of sample size and missing mechanisms. A demonstration of these five methods with PSA to evaluate the effect of participation in center-based care on children's reading ability is provided using data from the Early Childhood Longitudinal Study, Kindergarten Class of 2010-2011. (PsycInfo Database Record (c) 2024 APA, all rights reserved).


  • Open Access

    A Comparison of Random Forest-Based Missing Imputation Methods for Covariates in Propensity Score Analysis

    by Yongseok Lee, Walter Leite

    Propensity Score Analysis (PSA) is a prominent method to alleviate selection bias in observational studies, but missing data in covariates is prevalent and must be dealt with during propensity score estimation. Through Monte Carlo simulations, this study evaluates the use of imputation methods based on multiple random forests (RF) algorithms to handle missing data in covariates: MICE-RF (Caliber), Proximity Imputation (PI), and missForest. The results indicated that PI and missForest outperformed other methods with respect to a bias of average treatment effect (ATE) regardless of sample size and missing mechanisms. A demonstration of these five methods with PSA to evaluate the effect of participation in center-based care on children’s reading ability is provided using data from the Early Childhood Longitudinal Study (ECLS-K: 2011).

  • Propensity Score Matching with Cross-Classified Data Structures: A Comparison of Methods

    by Yongseok Lee, Walter L. Leite, Audrey J. Leroux

    In the current study, we compare propensity score (PS) matching methods for data with a cross-classified structure, where each individual is clustered within more than one group, but the groups are not hierarchically organized. Through a Monte Carlo simulation study, we compared sequential cluster matching (SCM), preferential within cluster matching (PWCM), greedy matching (GM), and optimal full matching (OFM), using propensity scores from four different models. The results indicated that the four matching methods performed well when PSs were estimated with logistic regression containing both level-1 and level-2 covariates. When the level-2 covariates were omitted in the logistic regression PS model, matching methods resulted in biased treatment effect estimates. However, omission of level-2 covariates did not result in biased estimates when the PS model was a logistic cross-classified random effects model (CCREM). SCM and PWCM outperformed GM and OFM with a logistic CCREM that included level-1 and level-2 covariates.


  • Open Access

    Propensity Score Matching with Cross-Classified Data Structures: A Comparison of Methods

    by Yongseok Lee, Walter Leite, Audrey Leroux

    In the current study, we compare propensity score (PS) matching methods for data with a cross-classified structure, where each individual is clustered within more than one group, but the groups are not hierarchically organized. Through a Monte Carlo simulation study, we compared sequential cluster matching, preferential within cluster matching, greedy matching, and optimal full matching, using propensity scores from four different models. We manipulated the correlation of random effects between crossed factors, degree of cross-classification, intra-unit correlation coefficient, variance explained by covariates, level-1 and level-2 sample sizes, and proportion treated. The results indicated that the four matching methods performed similarly when PSs were estimated with logistic regression containing both level-1 and level-2 covariates. Also, the matching methods were robust to the omission of all level-2 covariates if the PS model was a logistic cross-classified random effects model, which included random effects at both clustering levels.